Elastic Inference PNG and SVG Icon
Amazon Elastic Inference allows you to attach low-cost GPU-powered inference acceleration to Amazon EC2 and SageMaker instances.
Last Modified: August 29, 2025
16px
32px
48px
64px
Details
Key Features
- Attach GPU-powered inference acceleration to EC2 and SageMaker.
- Reduces ML inference costs by scaling GPU capacity as needed.
- Supports TensorFlow, Apache MXNet, and PyTorch.
- Pay only for the acceleration hours used.
Common Use Cases
- Reducing inference costs by attaching partial GPUs
- Accelerating deep learning model predictions
- Optimizing real-time AI workloads
Explore More Icons
IAM Identity Center
AWS IAM Identity Center (formerly AWS SSO) allows centralized access management to AWS accounts and business applications using single sign-on capabilities.
Infrastructure Composer
AWS Infrastructure Composer is a visual tool that helps developers create and deploy infrastructure using AWS CloudFormation templates more easily.
Security Hub
AWS Security Hub provides a comprehensive view of your security state in AWS by aggregating, organizing, and prioritizing security alerts and findings.
DeepLens
AWS DeepLens is a deep learning-enabled video camera for developers to run ML models locally on edge devices in real time.
Resilience Hub
AWS Resilience Hub helps you assess and improve the resilience of your applications using AWS best practices.
EC2
Amazon EC2 (Elastic Compute Cloud) is a web service that provides secure, resizable compute capacity in the cloud for virtually any workload.
AppConfig
AWS AppConfig is a capability of AWS Systems Manager that enables you to manage configuration changes across applications safely and rapidly.
Cloud Directory
Amazon Cloud Directory enables you to build flexible, cloud-native directories for organizing hierarchical data with multiple dimensions and relationships.
CodePipeline
AWS CodePipeline is a fully managed continuous delivery service that automates the build, test, and deployment phases of your release process.
App Studio
AWS App Studio is a development environment to build generative AI applications quickly using visual tools and built-in integrations.
HealthScribe
Amazon HealthScribe is a service that uses speech-to-text and generative AI to help clinicians automatically generate clinical notes from patient visits.
SageMaker Studio Lab
Amazon SageMaker Studio Lab is a free ML development environment that provides Jupyter-based tools for experimenting with models and datasets.
Mainframe Modernization
AWS Mainframe Modernization provides tools and infrastructure to migrate, run, and modernize mainframe applications on AWS.
EKS Anywhere
Amazon EKS Anywhere lets you create and operate Kubernetes clusters on your own infrastructure using the same tooling as Amazon EKS in the cloud.
DynamoDB
Amazon DynamoDB is a fully managed NoSQL database service designed to handle large-scale, high-availability workloads with low latency.
ECS Task
Amazon ECS Task is the smallest deployable unit in ECS, representing a single running container or group of containers defined by a task definition.
IoT Device Management
AWS IoT Device Management allows you to onboard, organize, monitor, and remotely manage IoT devices at scale throughout their lifecycle.
S3 on Outposts
Amazon S3 on Outposts brings object storage to on-premises environments using AWS Outposts, enabling data residency and low-latency workloads.
Deep Learning AMIs
AWS Deep Learning AMIs are pre-configured Amazon Machine Images optimized for ML frameworks such as TensorFlow, PyTorch, and MXNet.
AppSync
AWS AppSync is a fully managed service that makes it easy to develop GraphQL APIs by securely connecting to data sources like DynamoDB, Lambda, and more.
Client VPN
AWS Client VPN is a managed client-based VPN service that enables secure access to AWS resources and on-premises networks.
Keyspaces
Amazon Keyspaces is a scalable, highly available, and managed Apache Cassandra-compatible database service.
Thinkbox Krakatoa
Thinkbox Krakatoa is a volumetric particle rendering and manipulation software used in high-end VFX and simulation rendering.
Train
AWS Train refers to the process of building and optimizing machine learning models using training data on services like SageMaker.